Tracking the Intangible: Quantifying Effort in NFL Running Backs

Image source: The Tower

---

Introduction

Describe the problem and why it is important.

American Football is one of the most-watched and popular sports in the U.S., known for its quick decision-making, complex tactics, and athletically demanding displays of strength, endurance and speed.

Data

• Describe the data you’re using in detail, where you accessed it, along with relevant exploratory data analysis (EDA). You should also include descriptions of any relevant data pre-processing steps (e.g., whether you consider specific observations, create any meaningful features, etc.—but don’t mention minor steps like column type conversion, filtering out unnecessary rows)

• The data used for this project were from NFL Big Data Bowl 2022 Dataset (NFL Big Data Bowl 2022) on Kaggle.

• We limited our dataset to NFL running backs with more than 20 rushes.

Methods

• Describe the modeling techniques you chose, their assumptions, justifications for why they are appropriate for the problem, and how you’re comparing/evaluating the different methods.

• Used Dr. Ron Yurko and Quang Nguyen’s code to calculate distance from the nearest defender (Nguyen 2023)

• Based our AS/ AKE curved on the article titled “Individual acceleration-speed profile in-situ: A proof of concept in professional football players”(Morin et al. 2021)

• Still using the non-linear quantile regression plot? (Ding 2024)

Results

Describe your results. This can include tables and plots showing your results, as well as text describing how your models worked and the appropriate interpretations of the relevant output. (Note: Don’t just write out the textbook interpretations of all model coefficients. Instead, interpret the output that is relevant for your question of interest that is framed in the introduction)

Discussion

Give your conclusions and summarize what you have learned with regards to your question of interest. Are there any limitations with the approaches you used? What do you think are the next steps to follow-up your project?

Appendix

Non-linear quantile regression for acceleration vs speed

Interactive plot with menu for the 99th percentile

Percentage of total points that lie in between the percentile P_{99} and P_{99}-3

Metrics

Effort metric v2

• Percentage of total points that lie in between the percentile P_{99} and P_{99}-3
• This effort metric quantifies how often a player comes close to his “best” (99th percentile) accelerations

Tab 1: Top Running backs

Figure 1: Top 10

Tab 2: Bottom running backs

Figure 2: Bottom 10

Trying a different interactive layout

Tab 1: Saquon Barkley

Figure 3: trying non-linear-quant-regression

Tab 2: Rex Burkhead

Figure 4: trying out non-linear-quant-regression

Tab 3: Melvin Gordon

Figure 5: trying out non-linear-quant-regression

Tab 4: Chase Edmonds

Figure 6: trying out non-linear-quant-regression

Tab 5: Boston Scott

Figure 7: trying out non-linear-quant-regression

References

Ding, Peng. 2024. Linear Models and Extensions. Chapman & Hall. https://arxiv.org/pdf/2401.00649.

Morin, Jean-Benoit, Yann Le Mat, Cristian Osgnach, Andrea Barnabò, Alessandro Pilati, Pierre Samozino, and Pietro E. di Prampero. 2021. “Individual Acceleration-Speed Profile in-Situ: A Proof of Concept in Professional Football Players.” Journal of Biomechanics 123: 110524. https://doi.org/https://doi.org/10.1016/j.jbiomech.2021.110524.

NFL Big Data Bowl. 2022. “NFL Big Data Bowl 2022 Dataset.” Kaggle. https://www.kaggle.com/competitions/nfl-big-data-bowl-2022/data.

Nguyen, Quang. 2023. “Turn-Angle.” https://github.com/qntkhvn/turn-angle/blob/main/scripts/01a_prep_rusher_data.R.